GIFDL: Generated Image Fluctuation Distortion Learning for Enhancing Steganographic Security
- 23 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 4581-4594
Abstract
Minimum distortion steganography is currently the mainstream method for modification-based steganography. A key issue in this method is how to define steganographic distortion. With the rapid development of deep learning technology, the definition of distortion has evolved from manual design to deep learning design. Concurrently, rapid advancements in image generation have made generated images viable as cover media. However, existing distortion design methods based on machine learning do not fully leverage the advantages of generated cover media, resulting in suboptimal security performance. To address this issue, we propose GIFDL (Generated Image Fluctuation Distortion Learning), a steganographic distortion learning method based on the fluctuations in generated images. Inspired by the idea of natural steganography, we take a series of highly similar fluctuation images as the input to the steganographic distortion generator and introduce a new GAN training strategy to disguise stego images as fluctuation images. Experimental results demonstrate that GIFDL, compared with state-of-the-art GAN-based distortion learning methods, exhibits superior resistance to steganalysis, increasing the detection error rates by an average of 3.30% across three steganalyzers.Keywords
All Related Versions
Funding Information
- Natural Science Foundation of China (U2336206, 62472398, U2436601, 62402469)
This publication has 35 references indexed in Scilit:
- GAN-based adaptive cost learning for enhanced image steganography securityExpert Systems with Applications, 2024
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Image Disentanglement Autoencoder for Steganography without Embedding2022
- AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks2018
- Yedroudj-Net: An Efficient CNN for Spatial Steganalysis2018
- StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks2017
- A new cost function for spatial image steganography2014
- ImageNet: A large-scale hierarchical image database2009
- LSB matching revisitedIEEE Signal Processing Letters, 2006
- On the limits of steganographyIEEE Journal on Selected Areas in Communications, 1998